Triple

T12011968
Position Surface form Disambiguated ID Type / Status
Subject Oyá E285923 entity
Predicate spouse P13 FINISHED
Object Oshun E58293 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Oshun | Statement: [Oyá, spouse, Oshun]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Oshun
Context triple: [Oyá, spouse, Oshun]
  • A. Oshun chosen
    Oshun is a major Yoruba orisha revered as the goddess of fresh water, love, beauty, fertility, and diplomacy.
  • B. Oshunrinde
    Oshunrinde is the surname of Canadian record producer and songwriter WondaGurl, known for her work in hip-hop and contemporary popular music.
  • C. Yemoja
    Yemoja is a major Yoruba water deity revered as a nurturing mother figure and protector associated with rivers, fertility, and the sea.
  • D. Anahita
    Anahita is an ancient Iranian goddess associated with water, fertility, and protection, widely venerated in the Achaemenid and later Persian empires.
  • E. Alaqua
    Alaqua is a feminine given name most notably borne by American actress Alaqua Cox, known for her role in the Marvel Cinematic Universe.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d6ab45a368819084fce08bf0dc3705 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d903d7777481908cd5a001f75e2ee3 completed April 10, 2026, 2:06 p.m.
NED1 Entity disambiguation (via context triple) batch_69f48b363c6481908c8414c1eecc14f5 completed May 1, 2026, 11:15 a.m.
Created at: April 8, 2026, 9:46 p.m.